Back to library
Preview of slotstream
GitHub

Dev Utilities & Vibe-Coding Tooling · Local-first & sync

slotstream

Streams MoE experts from SSD so a 125B 4-bit Qwen can run on Macs with far less RAM, via MLX/Swift with an Ollama-compatible API.

Why it’s a gem

Makes huge local models practical on ordinary Mac memory budgets.

Visit github.com
Type
GitHub repository
License
MIT
Added
Sep 4, 2026

More from Local-first & sync